Architect AI pipelines that combine LLM-based ingestion, extraction, deduplication, quality checks, reasoning, and visualization.
Design agentic workflows that coordinate tools, functions, and data sources via orchestration frameworks.
Build user-facing agents that interpret queries, retrieve data, and generate tailored outputs using RAG.
Integrate AI applications into production, collaborating with product, engineering, and domain experts.
Develop generative interfaces for tasks like report generation, insight synthesis, and stakeholder communications.
Define LLM customization strategies, including fine-tuning, prompt engineering, and retrieval optimization.
Required Technical Skills
Prompt Engineering - Skilled in crafting and refining prompts for task-specific LLM behavior.
LLM APIs - Practical experience with APIs from OpenAI, Anthropic, or similar providers.
RAG & Embeddings - Familiarity with embedding models, vector stores, and retrieval-augmented generation patterns.
Agentic Development - Experience designing multi-step agent workflows with function calling and orchestration frameworks (e.g., CrewAI).
Software Development - Proficient in Python, Git, testing, and modern development practices.
NLP Techniques - Working knowledge of entity recognition, text classification, and model adaptation.
Evaluation & QA - Ability to define and track metrics for accuracy, latency, and hallucination in LLM agents.
Generative Visualization - Experience producing charts from RAG outputs using LLM-guided tools like Vega-Lite, Observable, or custom pipelines.
Education & Experience
Bachelor's degree in Computer Science, Software Engineering, Data Science, or a related field (or equivalent hands-on experience).
Two or more years developing production software, including at least one year building LLM-driven applications or AI agents.
Portfolio, GitHub repo, or case study demonstrating AI-enabled solutions in a real or simulated environment.
Bonus Skills
Understanding of LLM fine-tuning, agent orchestration frameworks such as CrewAI or LangChain, and open-source LLMs such as LLaMA, familiarity with AWS and Docker, hands-on experience with transformer libraries such as Hugging Face.
Job Type: Full-time
Pay: ?600,000.00 - ?1,200,000.00 per year
Work Location: In person
Beware of fraud agents! do not pay money to get a job
MNCJobsIndia.com will not be responsible for any payment made to a third-party. All Terms of Use are applicable.